Skip to main content
aifinhub
Risk & Portfolio Construction Worked Examples

Returns Distribution Analyzer: Examples

Short samples produce noisy higher moments; these scenarios are designed to show the direction of the change rather than any precise decimal. Skew measures asymmetry, excess kurtosis measures tail fatness relative to normal, and the Jarque-Bera statistic combines both into a normality test: a high statistic with a low p-value means non-normal returns. Compare what happens to these statistics as the series shifts from symmetric to skewed, and from thin-tailed to fat-tailed.

By AI Fin Hub Research · AI Fin Hub Team
Best Next MoveCalculators

Returns Distribution Analyzer

Paste a returns CSV. Histogram, normal-overlay, QQ plot, skewness, excess kurtosis, Jarque-Bera test, tail-weight index. See why Sharpe alone misleads.

CalculatorOpen ->

On This Page

Worked Examples

See the inputs and outcome together

Each scenario keeps the starting point, the outcome, and the actual lesson in one place so the page reads like a decision notebook, not a data dump.

  1. 1

    Symmetric series looks normal

    A balanced series of paired gains and losses around a zero mean. No asymmetry and no fat tails.

    Mean 0, skew 0, excess kurtosis minus 1.65, Jarque-Bera 1.36 (p = 0.51).

    Returns

    +/- 0.01, +/- 0.015, +/- 0.005, +/- 0.012, +/- 0.008, +/- 0.003

    Bins

    7

    Skew is exactly zero because the series is symmetric, and the Jarque-Bera p-value of 0.51 fails to reject normality. The negative excess kurtosis reflects a flat, platykurtic shape from the small evenly-spaced sample, not a tail problem. This is the clean baseline.

  2. 2

    Same calm, one crash day

    Nine small moves around zero plus a single minus-8-percent shock. The kind of tail event that defines real return series.

    Skew minus 2.19, excess kurtosis 3.32, Jarque-Bera 12.60 (p = 0.002).

    Returns

    0.005, 0.004, -0.003, 0.006, -0.002, 0.005, 0.003, -0.004, 0.005, -0.08

    Bins

    7

    One crash day drives skew to minus 2.19 and excess kurtosis to 3.32, and Jarque-Bera now rejects normality at p = 0.002. The median is still positive, so a naive look at central tendency would miss the risk entirely. Higher moments, not the average, expose tail danger.

  3. 3

    Mildly negative-skew series

    A series with frequent small gains and a few larger losses, the typical fingerprint of a short-volatility or carry strategy.

    Mean 0.002, skew minus 0.31, excess kurtosis minus 1.57, Jarque-Bera 1.19 (p = 0.55).

    Returns

    0.01, -0.02, 0.015, -0.005, 0.02, -0.01, 0.008, 0.012, -0.015, 0.005

    Bins

    5

    Skew is mildly negative at minus 0.31, hinting at asymmetric losses, but with only ten observations Jarque-Bera cannot reject normality (p = 0.55). The lesson is statistical power: a real negative-skew profile may need dozens of observations before the normality test can flag it.

Patterns

A symmetric series has zero skew and passes the Jarque-Bera normality test.
A single crash day flips skew sharply negative and pushes excess kurtosis positive, rejecting normality.
The mean and median can stay benign while the higher moments reveal tail risk, so do not judge a series by its average.
Short samples lack the statistical power to reject normality even when skew is visibly negative; sample size gates the verdict.

Try These Tools

Run the numbers next

Sources & References

Related Content

Keep the topic connected

Planning estimates only — not financial, tax, or investment advice.